System for the analysis of human balance based on accelerometers and support vector machines

Abstract

Disturbances in balance control lead to movement impairment and severe discomfort, dizziness, vertigo and may also lead to serious accidents. It is important to monitor the level of balance in order to determine the risk of a fall and to evaluate progress during treatment. Some solutions exist, but they are generally restricted to indoor environments. We propose and evaluate a system, based on accelerometers and support vector machines, that indicates the user’s postural balance variation which can be used in indoor and outdoor environments. For the training phase of the system, we used the accelerometer signals acquired from a single subject under monitored conditions of balance and intentional imbalance, and used the scores provided by the SWAY®software for establishing the reference target values. Based on these targets, we trained a support vector machine to classify the signal into n levels of balance and later evaluated the performance using cross validation by random resampling. We also developed a support vector machine approach for estimating the center of pressure, by using as reference targets the results from a force platform. For validation, we performed experiments with a subject who was performing determined movements. Later other experiments were executed, so the different centers of pressure could be computed by our system and compared to the results from the force platform. We also performed tests with a dummy and a John Doe doll, in order to observe the system’s behavior in the presence of a sudden drop or a lack of balance. The results show that the system can classify the acquired signals into two to seven levels of balance, with significant accuracy, and was also able to infer the centroid of each center of pressure region with an error lower than 0.9 cm. The tests performed with the dolls show that the system is able to distinguish between the conditions of a sudden drop and of a recovery of balance after losing one’s balance. The results suggest that the system can be used to detect variations in balance and, therefore, to indicate the risk of a fall even in outdoor environments.

Keywords

• Postural balance
• Balance signals processing
• Support vector machines
• Images processing
• Accelerometers